def test_probability_values_tree(data):
X, y = data
clf = SimilarityTreeClassifier()
clf.fit(X, y)
preds = clf.predict_proba(X)
assert_allclose(np.sum(preds, axis=1), np.ones(shape=y.shape))
def test_setting_attributes_tree(data):
X, y = data
clf = SimilarityTreeClassifier(random_state=42, n_directions=2)
clf.fit(X, y)
y_pred = clf.predict(X)
assert clf.random_state == 42
assert clf.n_directions == 2
def test_deterministic_predictions_tree():
X, y = make_blobs(n_samples=300, centers=[(0, 0), (1, 1)], random_state=42)
clf1 = SimilarityTreeClassifier(random_state=42)
clf1.fit(X, y)
clf2 = SimilarityTreeClassifier(random_state=42)
clf2.fit(X, y)
y_pred1 = clf1.predict(X)
y_pred2 = clf2.predict(X)
assert_array_equal(y_pred1, y_pred2)
def test_train_set_acc(data):
X, y = data
forest = SimilarityForestClassifier()
forest.fit(X, y)
# shouldn't be actually 1.0?
assert forest.score(X, y) > 0.8
tree = SimilarityTreeClassifier()
tree.fit(X, y)
assert tree.score(X, y) > 0.9
def test_similarity_tree_classifier_prediction(data):
X, y = data
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
random_state=42)
clf = SimilarityTreeClassifier()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
assert y_pred.shape == (X_test.shape[0], )
assert accuracy_score(y_test, y_pred) > 0.9
def test_log_probabilities_tree(data):
X, y = data
clf = SimilarityTreeClassifier()
clf.fit(X, y)
preds = clf.predict_proba(X)
log_preds = clf.predict_log_proba(X)
assert_allclose(log_preds, np.log(preds + 1e-10))
def test_pure_node():
X = np.ndarray(shape=(2, 2), dtype=float, order='F')
y = np.zeros(shape=(2, ), dtype=np.int64)
clf = SimilarityTreeClassifier()
clf.fit(X, y)
assert clf._is_leaf == True
def test_number_of_tree_leaves_in_apply(data):
X, y = data
clf = SimilarityTreeClassifier()
clf.fit(X, y)
assert (np.unique(clf.apply(X)).size == clf.get_n_leaves())